Related papers: A robust and efficient video representation for ac…
The recent trend in action recognition is towards larger datasets, an increasing number of action classes and larger visual vocabularies. State-of-the-art human action classification in challenging video data is currently based on a…
Many modern video-based human action recognition (HAR) approaches use 2D skeleton as the intermediate representation in their prediction pipelines. Despite overall encouraging results, these approaches still struggle in many common scenes,…
Complex scenes present significant challenges for predicting human behaviour due to the abundance of interaction information, such as human-human and humanenvironment interactions. These factors complicate the analysis and understanding of…
Deep homography estimation has broad applications in computer vision and robotics. Remarkable progresses have been achieved while the existing methods typically treat it as a direct regression or iterative refinement problem and often…
We consider the problem of estimating human pose and trajectory by an aerial robot with a monocular camera in near real time. We present a preliminary solution whose distinguishing feature is a dynamic classifier selection architecture. In…
Robustness to domain changes is a key capability for effective deployment of human action recognition systems in real-world scenarios, where action categories at inference can present important domain shifts or even unseen actions from…
Due to the rapid temporal and fine-grained nature of complex human assembly atomic actions, traditional action segmentation approaches requiring the spatial (and often temporal) down sampling of video frames often loose vital fine-grained…
This project investigates the human multi-modal behavior identification algorithm utilizing deep neural networks. According to the characteristics of different modal information, different deep neural networks are used to adapt to different…
Objects recognition in image is one of the most difficult problems in computer vision. It is also an important step for the implementation of several existing applications that require high-level image interpretation. Therefore, there is a…
This paper presents a new algorithm for online estimation of a sequence of homographies applicable to image sequences obtained from robotic vehicles equipped with vision sensors. The approach taken exploits the underlying Special Linear…
Although dense local spatial-temporal features with bag-of-features representation achieve state-of-the-art performance for action recognition, the huge feature number and feature size prevent current methods from scaling up to real size…
Analysis of human actions in videos demands understanding complex human dynamics, as well as the interaction between actors and context. However, these interaction relationships usually exhibit large intra-class variations from diverse…
The quality of recorded videos and images is significantly influenced by the camera's field of view (FOV). In critical applications like surveillance systems and self-driving cars, an inadequate FOV can give rise to severe safety and…
The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts…
Training robust deep video representations has proven to be much more challenging than learning deep image representations. This is in part due to the enormous size of raw video streams and the high temporal redundancy; the true and…
The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are…
Recent works have shown that combining object detection and tracking tasks, in the case of video data, results in higher performance for both tasks, but they require a high frame-rate as a strict requirement for performance. This is…
As research on action recognition matures, the focus is shifting away from categorizing basic task-oriented actions using hand-segmented video datasets to understanding complex goal-oriented daily human activities in real-world settings.…
Skeleton sequences are lightweight and compact, and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues,…
Video based action recognition is one of the important and challenging problems in computer vision research. Bag of Visual Words model (BoVW) with local features has become the most popular method and obtained the state-of-the-art…